Tag
This paper presents a two-level autoresearch framework where an outer-loop AI agent autonomously optimizes inner-loop LLM policy-synthesis pipelines for multi-agent sequential social dilemmas, achieving superior performance and discovering objective-specific mechanisms like fairness under a maximin welfare objective.
This research paper identifies the 'memory curse' in LLM agents, demonstrating that expanded context windows systematically degrade cooperative behavior in multi-agent social dilemmas by eroding forward-looking intent. The authors show that targeted fine-tuning, synthetic memory sanitization, and reducing explicit Chain-of-Thought reasoning can effectively mitigate this behavioral decay.